End of training

README.md

@@ -2,9 +2,15 @@
 license: llama2
 base_model: epfl-llm/meditron-7b
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: meditron-7b-dpo-full-wo-healthsearch_qa-ep3
   results: []
@@ -15,7 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # meditron-7b-dpo-full-wo-healthsearch_qa-ep3
 
-This model is a fine-tuned version of [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b) on an unknown dataset.
+This model is a fine-tuned version of [epfl-llm/meditron-7b](https://huggingface.co/epfl-llm/meditron-7b) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6786
+- Rewards/chosen: -0.0040
+- Rewards/rejected: -0.0362
+- Rewards/accuracies: 0.6245
+- Rewards/margins: 0.0322
+- Logps/rejected: -1242.8666
+- Logps/chosen: -1081.9209
+- Logits/rejected: -0.7759
+- Logits/chosen: -0.8007
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -0.8007283806800842,
+    "eval_logits/rejected": -0.7758755683898926,
+    "eval_logps/chosen": -1081.9208984375,
+    "eval_logps/rejected": -1242.8665771484375,
+    "eval_loss": 0.6785902976989746,
+    "eval_rewards/accuracies": 0.6244725584983826,
+    "eval_rewards/chosen": -0.003962064627557993,
+    "eval_rewards/margins": 0.032243408262729645,
+    "eval_rewards/rejected": -0.0362054705619812,
+    "eval_runtime": 850.5886,
+    "eval_samples": 7584,
+    "eval_samples_per_second": 8.916,
+    "eval_steps_per_second": 0.279,
     "train_loss": 0.6656996970591338,
     "train_runtime": 1292.3769,
     "train_samples": 5883,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32017
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -0.8007283806800842,
+    "eval_logits/rejected": -0.7758755683898926,
+    "eval_logps/chosen": -1081.9208984375,
+    "eval_logps/rejected": -1242.8665771484375,
+    "eval_loss": 0.6785902976989746,
+    "eval_rewards/accuracies": 0.6244725584983826,
+    "eval_rewards/chosen": -0.003962064627557993,
+    "eval_rewards/margins": 0.032243408262729645,
+    "eval_rewards/rejected": -0.0362054705619812,
+    "eval_runtime": 850.5886,
+    "eval_samples": 7584,
+    "eval_samples_per_second": 8.916,
+    "eval_steps_per_second": 0.279
+}